Improving 6D pose estimation of objects in clutter via physics-aware monte carlo tree search

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

This work proposes a process for efficiently searching over combinations of individual object 6D pose hypotheses in cluttered scenes, especially in cases involving occlusions and objects resting on each other. The initial set of candidate object poses is generated from state-of-the-art object detection and global point cloud registration techniques. The best scored pose per object by using these techniques may not be accurate due to overlaps and occlusions. Nevertheless, experimental indications provided in this work show that object poses with lower ranks may be closer to the real poses than ones with high ranks according to registration techniques. This motivates a global optimization process for improving these poses by taking into account scene-level physical interactions between objects. It also implies that the Cartesian product of candidate poses for interacting objects must be searched so as to identify the best scene-level hypothesis. To perform the search efficiently, the candidate poses for each object are clustered so as to reduce their number but still keep a sufficient diversity. Then, searching over the combinations of candidate object poses is performed through a Monte Carlo Tree Search (MCTS) process that uses the similarity between the observed depth image of the scene and a rendering of the scene given the hypothesized pose as a score that guides the search procedure. MCTS handles in a principled way the tradeoff between fine-tuning the most promising poses and exploring new ones, by using the Upper Confidence Bound (UCB) technique. Experimental results indicate that this process is able to quickly identify in cluttered scenes physically-consistent object poses that are significantly closer to ground truth compared to poses found by point cloud registration methods.

Original languageEnglish (US)
Title of host publication2018 IEEE International Conference on Robotics and Automation, ICRA 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3331-3338
Number of pages8
ISBN (Electronic)9781538630815
DOIs
StatePublished - Sep 10 2018
Event2018 IEEE International Conference on Robotics and Automation, ICRA 2018 - Brisbane, Australia
Duration: May 21 2018May 25 2018

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)1050-4729

Conference

Conference2018 IEEE International Conference on Robotics and Automation, ICRA 2018
CountryAustralia
CityBrisbane
Period5/21/185/25/18

Fingerprint

Global optimization
Physics
Tuning
Object detection

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

Mitash, C., Boularias, A., & Bekris, K. (2018). Improving 6D pose estimation of objects in clutter via physics-aware monte carlo tree search. In 2018 IEEE International Conference on Robotics and Automation, ICRA 2018 (pp. 3331-3338). [8461163] (Proceedings - IEEE International Conference on Robotics and Automation). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRA.2018.8461163
Mitash, Chaitanya ; Boularias, Abdeslam ; Bekris, Kostas. / Improving 6D pose estimation of objects in clutter via physics-aware monte carlo tree search. 2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 3331-3338 (Proceedings - IEEE International Conference on Robotics and Automation).
@inproceedings{6cbed8c1693d43c4a31b19578d55e624,
title = "Improving 6D pose estimation of objects in clutter via physics-aware monte carlo tree search",
abstract = "This work proposes a process for efficiently searching over combinations of individual object 6D pose hypotheses in cluttered scenes, especially in cases involving occlusions and objects resting on each other. The initial set of candidate object poses is generated from state-of-the-art object detection and global point cloud registration techniques. The best scored pose per object by using these techniques may not be accurate due to overlaps and occlusions. Nevertheless, experimental indications provided in this work show that object poses with lower ranks may be closer to the real poses than ones with high ranks according to registration techniques. This motivates a global optimization process for improving these poses by taking into account scene-level physical interactions between objects. It also implies that the Cartesian product of candidate poses for interacting objects must be searched so as to identify the best scene-level hypothesis. To perform the search efficiently, the candidate poses for each object are clustered so as to reduce their number but still keep a sufficient diversity. Then, searching over the combinations of candidate object poses is performed through a Monte Carlo Tree Search (MCTS) process that uses the similarity between the observed depth image of the scene and a rendering of the scene given the hypothesized pose as a score that guides the search procedure. MCTS handles in a principled way the tradeoff between fine-tuning the most promising poses and exploring new ones, by using the Upper Confidence Bound (UCB) technique. Experimental results indicate that this process is able to quickly identify in cluttered scenes physically-consistent object poses that are significantly closer to ground truth compared to poses found by point cloud registration methods.",
author = "Chaitanya Mitash and Abdeslam Boularias and Kostas Bekris",
year = "2018",
month = "9",
day = "10",
doi = "10.1109/ICRA.2018.8461163",
language = "English (US)",
series = "Proceedings - IEEE International Conference on Robotics and Automation",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "3331--3338",
booktitle = "2018 IEEE International Conference on Robotics and Automation, ICRA 2018",
address = "United States",

}

Mitash, C, Boularias, A & Bekris, K 2018, Improving 6D pose estimation of objects in clutter via physics-aware monte carlo tree search. in 2018 IEEE International Conference on Robotics and Automation, ICRA 2018., 8461163, Proceedings - IEEE International Conference on Robotics and Automation, Institute of Electrical and Electronics Engineers Inc., pp. 3331-3338, 2018 IEEE International Conference on Robotics and Automation, ICRA 2018, Brisbane, Australia, 5/21/18. https://doi.org/10.1109/ICRA.2018.8461163

Improving 6D pose estimation of objects in clutter via physics-aware monte carlo tree search. / Mitash, Chaitanya; Boularias, Abdeslam; Bekris, Kostas.

2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 3331-3338 8461163 (Proceedings - IEEE International Conference on Robotics and Automation).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Improving 6D pose estimation of objects in clutter via physics-aware monte carlo tree search

AU - Mitash, Chaitanya

AU - Boularias, Abdeslam

AU - Bekris, Kostas

PY - 2018/9/10

Y1 - 2018/9/10

N2 - This work proposes a process for efficiently searching over combinations of individual object 6D pose hypotheses in cluttered scenes, especially in cases involving occlusions and objects resting on each other. The initial set of candidate object poses is generated from state-of-the-art object detection and global point cloud registration techniques. The best scored pose per object by using these techniques may not be accurate due to overlaps and occlusions. Nevertheless, experimental indications provided in this work show that object poses with lower ranks may be closer to the real poses than ones with high ranks according to registration techniques. This motivates a global optimization process for improving these poses by taking into account scene-level physical interactions between objects. It also implies that the Cartesian product of candidate poses for interacting objects must be searched so as to identify the best scene-level hypothesis. To perform the search efficiently, the candidate poses for each object are clustered so as to reduce their number but still keep a sufficient diversity. Then, searching over the combinations of candidate object poses is performed through a Monte Carlo Tree Search (MCTS) process that uses the similarity between the observed depth image of the scene and a rendering of the scene given the hypothesized pose as a score that guides the search procedure. MCTS handles in a principled way the tradeoff between fine-tuning the most promising poses and exploring new ones, by using the Upper Confidence Bound (UCB) technique. Experimental results indicate that this process is able to quickly identify in cluttered scenes physically-consistent object poses that are significantly closer to ground truth compared to poses found by point cloud registration methods.

AB - This work proposes a process for efficiently searching over combinations of individual object 6D pose hypotheses in cluttered scenes, especially in cases involving occlusions and objects resting on each other. The initial set of candidate object poses is generated from state-of-the-art object detection and global point cloud registration techniques. The best scored pose per object by using these techniques may not be accurate due to overlaps and occlusions. Nevertheless, experimental indications provided in this work show that object poses with lower ranks may be closer to the real poses than ones with high ranks according to registration techniques. This motivates a global optimization process for improving these poses by taking into account scene-level physical interactions between objects. It also implies that the Cartesian product of candidate poses for interacting objects must be searched so as to identify the best scene-level hypothesis. To perform the search efficiently, the candidate poses for each object are clustered so as to reduce their number but still keep a sufficient diversity. Then, searching over the combinations of candidate object poses is performed through a Monte Carlo Tree Search (MCTS) process that uses the similarity between the observed depth image of the scene and a rendering of the scene given the hypothesized pose as a score that guides the search procedure. MCTS handles in a principled way the tradeoff between fine-tuning the most promising poses and exploring new ones, by using the Upper Confidence Bound (UCB) technique. Experimental results indicate that this process is able to quickly identify in cluttered scenes physically-consistent object poses that are significantly closer to ground truth compared to poses found by point cloud registration methods.

UR - http://www.scopus.com/inward/record.url?scp=85062267429&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062267429&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2018.8461163

DO - 10.1109/ICRA.2018.8461163

M3 - Conference contribution

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 3331

EP - 3338

BT - 2018 IEEE International Conference on Robotics and Automation, ICRA 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Mitash C, Boularias A, Bekris K. Improving 6D pose estimation of objects in clutter via physics-aware monte carlo tree search. In 2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 3331-3338. 8461163. (Proceedings - IEEE International Conference on Robotics and Automation). https://doi.org/10.1109/ICRA.2018.8461163